The main purpose of this study is to show that social inequalities in health can be measured by analysing the demographic and socioeconomic characteristics of neighbourhoods of residence. We take as an example the risk of very preterm birth in the Paris region, using data from the Épipage study. For the 1999 census in France, INSEE created new infra-communal census zones called IRIS 2000, and we use census data from these zones to determine the characteristics of different neighbourhoods. Social inequalities are analysed via an approach based on living conditions, which involves calculating a deprivation score using variables which best capture the different aspects of deprivation. We observe that 31% of mothers who gave birth prematurely live in the most disadvantaged neighbourhoods (last quartile of the deprivation score), while 21% live in the most affluent ones (first quartile). This excess risk corresponds to an odds ratio of 1.5. Our findings corroborate those of many other studies which have shown that the socioeconomic environment is linked to the risk of preterm birth: the more deprived the environment, the higher the risk. This methodology could be used for other health outcomes and would provide a means to monitor socio-spatial inequalities in epidemiological studies.